Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2990 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5363. Min Range: -6.5363
Max Act: 6.5363. Min Act: -0.1700
Data Index: 765706 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5363. Min Range: -6.5363
Max Act: 6.3175. Min Act: -0.1700
Data Index: 7542068 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5363. Min Range: -6.5363
Max Act: 6.2550. Min Act: -0.1700
Data Index: 4524844 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5363. Min Range: -6.5363
Max Act: 6.2238. Min Act: -0.1700
Data Index: 5187020 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5363. Min Range: -6.5363
Max Act: 6.1925. Min Act: -0.1700
Data Index: 719369 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5363. Min Range: -6.5363
Max Act: 6.1925. Min Act: -0.1700
Data Index: 654238 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5363. Min Range: -6.5363
Max Act: 6.1613. Min Act: -0.1700
Data Index: 879614 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5363. Min Range: -6.5363
Max Act: 6.1300. Min Act: -0.1700
Data Index: 879619 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5363. Min Range: -6.5363
Max Act: 6.1300. Min Act: -0.1700
Data Index: 5763042 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5363. Min Range: -6.5363
Max Act: 6.0988. Min Act: -0.1700
Data Index: 5318879 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5363. Min Range: -6.5363
Max Act: 6.0675. Min Act: -0.1700
Data Index: 4372936 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5363. Min Range: -6.5363
Max Act: 6.0988. Min Act: -0.1700
Data Index: 4524843 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5363. Min Range: -6.5363
Max Act: 6.0988. Min Act: -0.1700
Data Index: 5679953 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5363. Min Range: -6.5363
Max Act: 6.0363. Min Act: -0.1700
Data Index: 1948846 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5363. Min Range: -6.5363
Max Act: 6.0988. Min Act: -0.1700
Data Index: 879615 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5363. Min Range: -6.5363
Max Act: 6.0988. Min Act: -0.1700
Data Index: 613353 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5363. Min Range: -6.5363
Max Act: 6.0675. Min Act: -0.1700
Data Index: 1948844 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5363. Min Range: -6.5363
Max Act: 6.0675. Min Act: -0.1700
Data Index: 1267598 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5363. Min Range: -6.5363
Max Act: 6.0050. Min Act: -0.1700
Data Index: 4899731 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5363. Min Range: -6.5363
Max Act: 6.0675. Min Act: -0.1700
Data Index: 879616 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #19